Songchun Zhang
4 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
sparse view
(2)
diffusion model
(2)
novel view synthesis
(2)
3d reconstruction
(2)
video diffusion
(1)
epipolar attention
(1)
3d gaussian
(1)
sparse-view reconstruction
(1)
3d scene generation
(1)
3d scene reconstruction
(1)
video diffusion model
(1)
diffusion transformer
(1)
3d consistency
(1)
text-driven generation
(1)
gaussian primitive
(1)
3d gaussian primitive
(1)
generative refinement
(1)
multiview conditional
(1)
text-driven 3d generation
(1)
visual concept composition
(1)
Papers
Composing Concepts from Images and Videos via Concept-prompt Binding
CVPR 2026
Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views
AAAI 2025
SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
ICCV 2025
3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
CVPR 2024