activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Haian Jin, Rundi Wu, Tianyuan Zhang +4

Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and have a computational cost that scales quadratically wi…

cs.CV2026

GR3EN: Generative Relighting for 3D Environments

Xiaoyan Xing, Philipp Henzler, Junhwa Hur +4

We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-con…

cs.CV2025

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

Alexander Mai, Peter Hedman, George Kopanas +6

We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recent rasterization based approach by 3D Gauss…

cs.CV2024

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

Hadi Alzayer, Philipp Henzler, Jonathan T. Barron +3

Reconstructing the geometry and appearance of objects from photographs taken in different environments is difficult as the illumination and therefore the object appearance vary acr…

cs.CV2024

Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering

Benjamin Attal, Dor Verbin, Ben Mildenhall +4

State-of-the-art techniques for 3D reconstruction are largely based on volumetric scene representations, which require sampling multiple points to compute the color arriving along…

cs.CV2024

SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration

Daniel Duckworth, Peter Hedman, Christian Reiser +5

Recent techniques for real-time view synthesis have rapidly advanced in fidelity and speed, and modern methods are capable of rendering near-photorealistic scenes at interactive fr…