Tech
AI method reconstructs 3D scene details from simulated images using inverse rendering
Over the past decades, computer scientists have developed many computational tools that can analyze and interpret images. These tools have proved useful for a broad range of applications, including robotics, autonomous driving, health care, manufacturing and even entertainment.
Most of the best performing computer vision approaches employed to date rely on so-called feed-forward neural networks. These are computational models that process input images step by step, ultimately making predictions about them.
While some of these models were found to perform well when tested on the data they analyzed during training, they often do not generalize well across new images and in different scenarios. In addition, their predictions and the patterns they extract from images can be difficult to interpret.
Researchers at Princeton University recently developed a new inverse rendering approach that is more transparent and could also interpret a wide range of images more reliably. The new approach, introduced in a paper published in Nature Machine Intelligence, relies on a generative artificial intelligence (AI)-based method to simulate the process of image creation, while also optimizing it by gradually adjusting a model’s internal parameters.
“Generative AI and neural rendering have transformed the field in recent years for creating novel content: producing images or videos from scene descriptions,” Felix Heide, senior author of the paper, told Tech Xplore. “We investigate whether we can flip this around and use these generative models for extracting the scene descriptions from images.”
The new approach developed by Heide and his colleagues relies on a so-called differentiable rendering pipeline. This is a process for the simulation of image creation, relying on compressed representations of images created by generative AI models.
“We developed an analysis-by-synthesis approach that allows us to solve vision tasks, such as tracking, as test-time optimization problems,” explained Heide. “We found that this method generalizes across datasets, and in contrast to existing supervised learning methods, does not need to be trained on new datasets.”
Essentially, the method developed by the researchers works by placing models of 3D objects in a virtual scene depicting real world settings. These models of objects are generated by a generative AI based on random sample of 3D scene parameters.
“We then render all these objects back together into a 2D image,” said Heide. “Next, we compare this rendered image with the real observed image. Based on how different they are, we backpropagate the difference through both the differentiable rendering function and the 3D generation model to update its inputs. In just a few steps, we optimize these inputs to make the rendered match the observed images better.”
-

Optimizing 3D models through inverse neural rendering. From left to right: the observed image, initial random 3D generations, and three optimization steps that refine these to better match the observed image. The observed images are faded to show the rendered objects clearly. The method effectively refines object appearance and position, all done at test time with inverse neural rendering. Credit: Ost et al.
-

Generalization of 3D multi-object tracking with Inverse Neural Rendering. The method directly generalizes across datasets such as the nuScenes and Waymo Open Dataset benchmarks without additional fine-tuning and is trained on synthetic 3D models only. The observed images are overlaid with the closest generated object and tracked 3D bounding boxes. Credit: Ost et al.
A notable advantage of the team’s newly proposed approach is that it allows very generic 3D object generation models trained on synthetic data to perform well across a wide range of datasets containing images captured in real-world settings. In addition, the renderings produced by the models are far more explainable than those produced by conventional rendering tools based on feed-forward machine learning models.
“Our inverse rendering approach for tracking works just as well as learned feed-forward approaches, but it provides us with explicit 3D explanations of its perceived world,” said Heide.
“The other interesting aspect is the generalization capabilities. Without changing the 3D generation model or training it on new data, our 3D multi-object tracking through Inverse Neural Rendering works well across different autonomous driving datasets and object types. This can significantly reduce the cost of fine-tuning on new data or at least work as an auto-labeling pipeline.”
This recent study could soon help to advance AI models for computer vision, improving their performance in real-world settings while also increasing their transparency. The researchers now plan to continue improving their method and start testing it on more computer vision-related tasks.
“A logical next step is the expansion of the proposed approach to other perception tasks, such as 3D detection and 3D segmentation,” added Heide. “Ultimately, we want to explore if inverse rendering can even be used to infer the whole 3D scene, and not just individual objects. This would allow our future robots to reason and continuously optimize a three-dimensional model of the world, which comes with built-in explainability.”
Written for you by our author Ingrid Fadelli,
edited by Gaby Clark, and fact-checked and reviewed by Robert Egan—this article is the result of careful human work. We rely on readers like you to keep independent science journalism alive.
If this reporting matters to you,
please consider a donation (especially monthly).
You’ll get an ad-free account as a thank-you.
More information:
Julian Ost et al, Towards generalizable and interpretable three-dimensional tracking with inverse neural rendering, Nature Machine Intelligence (2025). DOI: 10.1038/s42256-025-01083-x.
© 2025 Science X Network
Citation:
AI method reconstructs 3D scene details from simulated images using inverse rendering (2025, August 23)
retrieved 23 August 2025
from https://techxplore.com/news/2025-08-ai-method-reconstructs-3d-scene.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
Tech
Former USDS Leaders Launch Tech Reform Project to Fix What DOGE Broke
The past year has been traumatic for many of the volunteer tech warriors of what was once called the United States Digital Service (USDS). The team’s former coders, designers, and UX experts have watched in horror as Donald Trump rebranded the service as DOGE, effectively forced out its staff, and employed a strike force of young and reckless engineers to dismantle government agencies under the guise of eliminating fraud. But one aspect of the Trump initiative triggered envy in tech reformers: the Trump administration’s fearlessness in upending generations of cruft and inertia in government services. What if government leaders actually used that decisiveness and clout in service of the people instead of following the murky agendas of Donald Trump or DOGE maestro Elon Musk?
A small though influential team is proposing to answer that exact question, working on a solution they hope to deploy during the next Democratic administration. The initiative is called Tech Viaduct, and its goal is to create a complete plan to reboot how the US delivers services to citizens. The Viaduct cadre of experienced federal tech officials is in the process of cooking up specifics on how to remake the government, aiming to produce initial recommendations by the spring. By 2029, if a Democrat wins, it hopes to have its plan adopted by the White House.
Tech Viaduct’s advisory panel includes former Obama chief of staff and Biden’s secretary of Veterans Affairs Denis McDonough; Biden’s deputy CTO Alexander Macgillivray; Marina Nitze, former CTO of the VA; and Hillary Clinton campaign manager Robby Mook. But most attention-grabbing is its senior adviser and spiritual leader, Mikey Dickerson, the crusty former Google engineer who was the first leader of USDS. His hands-on ethic and unfiltered distaste for bureaucracy embodied the spirit of Obama’s tech surge. No one is more familiar with how government tech services fail American citizens than Dickerson. And no one is more disgusted with the various ways they have fallen short.
Dickerson himself unwittingly put the Viaduct project in motion last April. He was packing up the contents of his DC-area condo to move as far away as possible from the political scrum (to an abandoned sky observatory in a remote corner of Arizona) when McDonough suggested he meet with Mook. When the two got together, they bemoaned the DOGE initiative but agreed that the impulse to shred the dysfunctional system and start over was a good one. “The basic idea is that it’s too hard to get things done,” says Dickerson. “They’re not wrong about that.” He admits that Democrats had blown a big opportunity “For 10 years we’ve had tiny wins here and there but never terraformed the whole ecosystem,” Dickerson says. “What would that look like?”
Dickerson was surprised a few months later when Mook called him to say he found funding from Searchlight Institute, a liberal think tank devoted to novel policy initiatives, to get the idea off the ground. (A Searchlight spokesperson says that the think tank is budgeting $1 million for the project.) Dickerson, like Al Pacino in Godfather III, was pulled back in. Ironically, it was Trump’s reckless-abandon approach to government that convinced him that change was possible. “When I was there, we were severely outgunned, 200 people running around trying to improve websites,” he says. “Trump has knocked over all the beehives—the beltway bandits, the contractor industrial complex, the union industrial complex.”
Tech Viaduct has two aims. The first is to produce a master plan to remake government services—establishing an unbiased procurement process, creating a merit-based hiring process, and assuring oversight to make sure things don’t go awry. (Welcome back, inspector generals!) The idea is to design signature-ready executive orders and legislative drafts that will guide the recruiting strategy for a revitalized civil service. In the next few months, the group plans to devise and test a framework that could be executed immediately in 2029, without any momentum-killing consensus building. In Viaduct’s vision that consensus will be achieved before the election. “Thinking up bright ideas is going to be the easy part,“ Dickerson says. “As hard as we’re going to work in the next three to six months, we’re going to have to spend another two to three years, through a primary season and through an election, advocating as if we were a lobbying group.”
Tech
Why Everyone Is Suddenly in a ‘Very Chinese Time’ in Their Lives
In case you didn’t get the memo, everyone is feeling very Chinese these days. Across social media, people are proclaiming that “You met me at a very Chinese time of my life,” while performing stereotypically Chinese-coded activities like eating dim sum or wearing the viral Adidas Chinese jacket. The trend blew up so much in recent weeks that celebrities like comedian Jimmy O Yang and influencer Hasan Piker even got in on it. It has now evolved into variations like “Chinamaxxing” (acting increasingly more Chinese) and “u will turn Chinese tomorrow” (a kind of affirmation or blessing).
It’s hard to quantify a zeitgeist, but here at WIRED, chronically online people like us have been noticing a distinct vibe shift when it comes to China over the past year. Despite all of the tariffs, export controls, and anti-China rhetoric, many people in the United States, especially younger generations, have fallen in love with Chinese technology, Chinese brands, Chinese cities, and are overall consuming more Chinese-made products than ever before. In a sense the only logical thing left to do was to literally become Chinese.
“It has occurred to me that a lot of you guys have not come to terms with your newfound Chinese identity,” the influencer Chao Ban joked in a TikTok video that has racked up over 340,000 likes. “Let me just ask you this: Aren’t you scrolling on this Chinese app, probably on a Chinese made phone, wearing clothes that are made in China, collecting dolls that are from China?”
Everything Is China
As is often the case with Western narratives about China, these memes are not really meant to paint an accurate picture of life in the country. Instead, they function as a projection of “all of the undesirable aspects of American life—or the decay of the American dream,” says Tianyu Fang, a PhD researcher at Harvard who studies science and technology in China.
At a moment when America’s infrastructure is crumbling and once-unthinkable forms of state violence are being normalized, China is starting to look pretty good in contrast. “When people say it’s the Chinese century, part of that is this ironic defeat,” says Fang.
As the Trump administration remade the US government in its own image and smashed long-standing democratic norms, people started yearning for an alternative role model, and they found a pretty good one in China. With its awe-inspiring skylines and abundant high-speed trains, the country serves as a symbol of the earnest and urgent desire among many Americans for something completely different from their own realities.
Critics frequently point to China’s massive clean energy investments to highlight America’s climate policy failures, or they point to its urban infrastructure development to shame the US housing shortage. These narratives tend to emphasize China’s strengths while sidelining the uglier facets of its development—but that selectivity is the point. China is being used less as a real place than as an abstraction, a way of exposing America’s own shortcomings. As writer Minh Tran observed in a recent Substack post, “In the twilight of the American empire, our Orientalism is not a patronizing one, but an aspirational one.”
Part of why China is on everyone’s mind is that it’s become totally unavoidable. No matter where you live in the world, you are likely going to be surrounded by things made in China. Here at WIRED, we’ve been documenting that exhaustively: Your phone or laptop or robot vacuum is made in China; your favorite AI slop joke is made in China; Labubu, the world’s most coveted toy, is made in China; the solar panels powering the Global South are made in China; the world’s best-selling EV brand, which officially overtook Tesla last year, is made in China. Even the most-talked about open-source AI model is from China. All of these examples are why this newsletter is called Made in China.
Tech
VTL Group boosts output by 10% with Coats Digital’s GSDCost solution
With over 5,000 employees and 3,000 sewing machines across 90 sewing lines, VTL Group specialises in jersey knits and denim, producing up to 20 million garments per year for world-renowned brands such as Lacoste, Adidas, G-Star, Hugo Boss, Replay and Paul & Shark. The company operates six garment production units, along with dedicated facilities for screen printing, knitting, dyeing and textile finishing. This extensive vertical integration gives VTL complete control over quality, lead-times and cost-efficiency, which is vital for meeting the stringent demands of its global customer base.
VTL Group has adopted Coats Digital’s GSDCost to standardise production, boost productivity, and improve pricing accuracy across its Tunisian operations.
The solution cut SMVs by 15–20 per cent, raised line output by 10 per cent, and enhanced planning, cost accuracy, and customer confidence, enabling competitive pricing, lean operations, and stronger relationships with global fashion brands.
Prior to implementing GSDCost, VTL calculated capacity and product pricing using data from internal time catalogues stored in Excel. This approach led to inconsistent and inaccurate cost estimations, causing both lost contracts due to inflated production times and reduced margins from underestimations. In some cases, delays caused by misaligned time predictions resulted in increased transportation costs and operational inefficiencies that impacted customer satisfaction.
Hichem Kordoghli, Plant Manager, VTL Group, said: “Before GSDCost, we struggled with inconsistent operating times that directly impacted our competitiveness. We lost orders when our timings were too high and missed profits when they were too low. GSDCost has transformed the way we approach planning, enabling us to quote confidently with accurate, reliable data. We’ve already seen up to 20% reductions in SMVs, a 10% rise in output, and improved customer confidence. It’s a game-changer for our sales and production teams.”
Since adopting GSDCost across 50 sewing lines, VTL Group has been able to establish a reliable baseline for production planning and line efficiency monitoring. This has led to a more streamlined approach to managing load plans and forecasting. Importantly, GSDCost has given the business the flexibility to align pricing more effectively with actual production realities, contributing to greater customer satisfaction and improved profit margins.
Although it’s too early to determine the exact financial impact, VTL Group has already realised improvements in pricing flexibility and competitiveness thanks to shorter product times and better planning. These gains are seen as instrumental in enabling the company to pursue more strategic orders, reduce wasted effort and overtime, and maintain the high expectations of leading global fashion brands.
Hichem Kordoghli, Plant Manager, VTL Group, added: “GSDCost has empowered our teams with reliable data that has translated directly into real operational benefits. We are seeing more consistent line performance, enhanced planning precision, and greater confidence across departments. These improvements are helping us build stronger relationships with our brand partners, while setting the foundation for sustainable productivity gains in the future.”
The company now plans to expand usage across an additional 30 lines in 2025, supported by a second phase of GSD Practitioner Bootcamp training to strengthen in-house expertise and embed best practices throughout the production environment. A further 10 lines are expected to follow in 2026 as part of VTL’s phased rollout strategy.
Liz Bamford, Customer Success Manager, Coats Digital, commented: “We are proud to support VTL Group in their digital transformation journey. The impressive improvements in planning accuracy, quoting precision, and cross-functional alignment are a testament to their commitment to innovation and excellence. GSDCost is helping VTL set a new benchmark for operational transparency and performance in the region, empowering their teams with the tools needed for long-term success.”
GSDCost, Coats Digital’s method analysis and pre-determined times solution, is widely acknowledged as the de-facto international standard across the sewn products industry. It supports a more collaborative, transparent, and sustainable supply chain in which brands and manufacturers establish and optimise ‘International Standard Time Benchmarks’ using standard motion codes and predetermined times. This shared framework supports accurate cost prediction, fact-based negotiation, and a more efficient garment manufacturing process, while concurrently delivering on CSR commitments.
Key Benefits and ROI for VTL Group
- 15–20% reduction in SMVs across 50 production lines
- 10% productivity increase across key sewing facilities
- More competitive pricing for strategic sales opportunities
- Improved cost accuracy and quotation flexibility
- Standardised time benchmarks for future factory expansion
- Enhanced planning accuracy and load plan management
- Greater alignment with lean and sustainable manufacturing goals
- Increased brand confidence and satisfaction among premium customers
Note: The headline, insights, and image of this press release may have been refined by the Fibre2Fashion staff; the rest of the content remains unchanged.
Fibre2Fashion News Desk (HU)
-
Politics1 week agoUK says provided assistance in US-led tanker seizure
-
Entertainment1 week agoDoes new US food pyramid put too much steak on your plate?
-
Entertainment1 week agoWhy did Nick Reiner’s lawyer Alan Jackson withdraw from case?
-
Sports6 days agoClock is ticking for Frank at Spurs, with dwindling evidence he deserves extra time
-
Business1 week agoTrump moves to ban home purchases by institutional investors
-
Sports1 week agoPGA of America CEO steps down after one year to take care of mother and mother-in-law
-
Tech4 days agoNew Proposed Legislation Would Let Self-Driving Cars Operate in New York State
-
Sports7 days ago
Commanders go young, promote David Blough to be offensive coordinator
