30 papers
HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
Tao Hu, Varun Jampani
Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In t…
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
Jan-Niklas Dihlmann, Mark Boss, Simon Donne +3
Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitation…
Human Video Generation from a Single Image with 3D Pose and View Control
Tiantian Wang, Chun-Han Yao, Tao Hu +3
Recent diffusion methods have made significant progress in generating videos from single images due to their powerful visual generation capabilities. However, challenges persist in…
GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
Mateusz Michalkiewicz, Anekha Sokhal, Tadeusz Michalkiewicz +4
Modern monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet recent works cast doubt on their true unders…
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
Viraj Shah, Nataniel Ruiz, Forrester Cole +4
Methods for finetuning generative models for concept-driven personalization generally achieve strong results for subject-driven or style-driven generation. Recently, low-rank adapt…
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting
Worameth Chinchuthakun, Pakkapon Phongthawee, Amit Raj +3
We introduce a simple yet effective technique for estimating lighting from a single low-dynamic-range (LDR) image by reframing the task as a chrome ball inpainting problem. This ap…