![]()
Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images
ICCV, 2025
project page
/
arXiv
We leverage a diffusion model and a depth predictor to generate high-quality scene geometry from a single image. Then, we distill a feed-forward scene reconstruction model, which performs on par with reconstruction methods trained with multi-view supervision. ![]()
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
ICCV, 2025 (Oral)
project page
/
arXiv
A method for consistent dynamic scene reconstruction via motion decoupling, bundle adjustment, and global refinement. ![]()
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
ICCV, 2025
project page
/
arXiv
/
code
/
demo
SceneDINO is unsupervised and infers 3D geometry and features from a single image in a feed-forward manner. Distilling and clustering SceneDINO's 3D feature field results in unsupervised semantic scene completion predictions. SceneDINO is trained using multi-view self-supervision. ![]()
AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
CVPR, 2025
project page
/
paper
/
code
A method for learning camera poses and intrinsics from dynamic casual videos. ![]()
Cache Me if You Can: Accelerating Diffusion Models through Block Caching
CVPR, 2024
project page
/
arXiv
/
video
We reuse layer computations from previous timesteps to make image generation with diffusion models more efficient. ![]()
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation
CVPR, 2024
project page
/
arXiv
/
video
/
code
Leveraging multi-view supervision and distillation training to improve volumetric reconstruction from a single image. ![]()
ControlRoom3D: Room Generation using Semantic Proxy Rooms
CVPR, 2024
project page
/
arXiv
/
video
ControlRoom3D creates diverse and plausible 3D room meshes aligning well with user-defined room layouts and textual descriptions of the room style. ![]()
S4C: Self-Supervised Semantic Scene Completion with Neural Fields
3DV, 2024 (Spotlight)
project page
/
arXiv
/
code
A self-supervised method for semantic scene completion, that rivals supervised approaches. ![]()
Behind the Scenes: Density Fields for Single View Reconstruction
CVPR, 2023
project page
/
arXiv
/
code
/
video
A self-supervised method for implicit volumetric reconstruction from a single image. ![]()
De-rendering 3D Objects in the Wild
CVPR, 2022
project page
/
arXiv
/
code
/
video
A self-supervised method for intrinsic image decomposition. ![]()
MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
CVPR, 2021
project page
/
arXiv
/
code
/
video
A state-of-the-art semi-supervised monocular dense reconstruction system, that utilizes a multi-view stereo approach with a filter for moving objects to predict depth maps in dynamic environments. |