MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms
Paper
•
2410.18977
•
Published
•
13
star
-
-
FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors
Paper • 2410.16271 • Published • 80 -
GS^3: Efficient Relighting with Triple Gaussian Splatting
Paper • 2410.11419 • Published • 10 -
ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion
Paper • 2410.08168 • Published • 7 -
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Paper • 2410.07707 • Published • 3 -
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders
Paper • 2410.22366 • Published • 70