Hugging Face Trending Papers
Albedo Estimation via Latent Bridge Matching
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Sep 10
Albedo Estimation via Latent Bridge Matching
arXiv:2609.09884v1 Announce Type: new Abstract: Recent advances in Intrinsic Image Decomposition (IID) have increasingly relied on generative models. However, progress remains limited by three key ch...
arXiv Computer Vision
Sep 1
MVID: Feed-Forward Multi-View Intrinsic Image Decomposition
arXiv:2512.23667v3 Announce Type: replace Abstract: Intrinsic image decomposition aims to recover material and illumination factors from RGB observations, but real-world images entangle reflectance w...
Hugging Face Trending Papers
3d ago
Real-Time Volumetric Light Transport Inference without a Path
The paper introduces a real‑time technique for reconstructing fully integrated pixel radiance in volumetric media under both direct and ambient illumination. It bypasses expensive path‑traced radiance estimates by inferring the final light‑transport solution from compact scene features and statistics, using an attention‑augmented image‑to‑image network. The method achieves high reconstruction accuracy in challenging volumetric cloud scenarios while maintaining stable computational cost regardless of camera zoom or volume density.
arXiv Computer Vision
6d ago
Integrating Learned Priors through Prior-Space Reparameterization for Physically Based Inverse Rendering
The paper introduces a prior-guided material reparameterization for physically based inverse rendering, leveraging learned material predictions to restrict the optimization space without altering the photometric objective. By fusing multi-view predictions onto a mesh and constructing a permutohedral lattice in prior feature space, surface points with similar predictions share material variables, which are jointly optimized with geometry and illumination. Experiments on synthetic benchmarks and Stanford-ORB show improved material decomposition and relighting, with PSNR gains of 1.5–2.5 dB over strong baselines and a faster optimization schedule that maintains high relighting quality.
arXiv AI
Aug 26
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
arXiv:2407.00500v2 Announce Type: replace-cross Abstract: Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes....
arXiv Computer Vision
Sep 11
Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models
The paper introduces a benchmark called Shedding Light to evaluate how well generative image models understand and reproduce lighting. The benchmark tests models by asking them to inpaint a simple object, called a light probe, into real photographs and then compares the generated probe to the ground truth to assess lighting direction, colour, and radiance. The authors provide a scalable protocol and open-source code and data for systematic assessment of photometric accuracy in future models.