Dan Xu

danxuhk's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 6 days ago

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention

Paper • 2512.01540 • Published 9 days ago • 3

upvoted a paper 6 days ago

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention

Paper • 2512.01540 • Published 9 days ago • 3

authored a paper 13 days ago

One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control

Paper • 2511.18922 • Published 16 days ago • 10

upvoted a paper 14 days ago

One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control

Paper • 2511.18922 • Published 16 days ago • 10

authored a paper about 1 month ago

FullPart: Generating each 3D Part at Full Resolution

Paper • 2510.26140 • Published Oct 30 • 6

upvoted a paper about 1 month ago

FullPart: Generating each 3D Part at Full Resolution

Paper • 2510.26140 • Published Oct 30 • 6

authored a paper about 2 months ago

Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos

Paper • 2510.18489 • Published Oct 21 • 5

upvoted 2 papers about 2 months ago

Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos

Paper • 2510.18489 • Published Oct 21 • 5

CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving

Paper • 2510.07944 • Published Oct 9 • 24

authored a paper about 2 months ago

Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction

Paper • 2510.04759 • Published Oct 6 • 9

upvoted 2 papers 2 months ago

Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction

Paper • 2510.04759 • Published Oct 6 • 9

DiGA3D: Coarse-to-Fine Diffusional Propagation of Geometry and Appearance for Versatile 3D Inpainting

Paper • 2507.00429 • Published Jul 1 • 1

authored a paper 3 months ago

HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

Paper • 2509.17083 • Published Sep 21 • 7

upvoted a paper 3 months ago

HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis

Paper • 2509.17083 • Published Sep 21 • 7

liked a model 3 months ago

Mifucius/ThinkDiff

Updated Sep 7 • 2

upvoted 2 papers 4 months ago

From One to More: Contextual Part Latents for 3D Generation

Paper • 2507.08772 • Published Jul 11 • 25

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Paper • 2507.21049 • Published Jul 28 • 40

authored 3 papers 5 months ago

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

Paper • 2312.04963 • Published Dec 7, 2023 • 17

Interactive3D: Create What You Want by Interactive 3D Generation

Paper • 2404.16510 • Published Apr 25, 2024 • 21

From One to More: Contextual Part Latents for 3D Generation

Paper • 2507.08772 • Published Jul 11 • 25