Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering

[2407.00500] Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2407.00500 (cs) [Submitted on 29 Jun 2024 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering Authors: Alireza Moazeni , Shichong Peng , Yanshu Zhang , Chirag Vashist , Ke Li View PDF HTML (experimental) Abstract: Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes. However, we identify a fundamental limitation: these methods suffer from a misattribution issue, where individual primitives learn incorrect appearance features despite producing correct aggregated renderings. We show that the root cause lies in volume rendering, which aggregates translucent primitives along each ray and only supervises the final colour, preventing direct supervision of individual primitive features. To address this, we propose Intrinsic PAPR, a robust intrinsic decomposition framework which leverages Proximity Attention Point Rendering (PAPR) to enable direct per-point supervision. Unlike volume rendering approaches, PAPR eliminates translucent primitives and directly predicts appearance at ray-surface intersections, enabling accurate supervision to the feature of each individual point. Our method incorporates a 2D albedo prior adapted with conditional Implicit Maximum Likelihood Estimation (cIMLE) to handle monocular ambiguities, and employs a space carving loss to ensure multi-view consistency. Extensive evaluations on synthetic and real-world datasets demonstrate that Intrinsic PAPR outperforms point-based inverse rendering, NeRF-based intrinsic decomposition, and diffusion-based PBR methods in novel view synthesis and albedo estimation while resolving the misattribution issue. Comments: Accepted to ECCV 2026. 21 pages + 34-page supplementary material Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG) Cite as: arXiv:2407.00500 [cs.CV] (or arXiv:2407.00500v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2407.00500 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Alireza Moazeni [ view email ] [v1] Sat, 29 Jun 2024 17:46:10 UTC (37,812 KB) [v2] Mon, 24 Aug 2026 20:56:44 UTC (36,715 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2024-07 Change to browse by: cs cs.AI cs.GR cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering#670285
• Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning#1071120
• StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Images#1143193
• 2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting#635777
• 2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting#633428