Search Results for author:
Found 8 papers, 4 papers with code
FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation
Estimating relative camera poses between images has been a central problem in computer vision.
Scalable 3D Captioning with Pretrained Models
We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects.
The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs
We present a simple baseline for directly estimating the relative pose (rotation and translation, including scale) between two images.
PlaneFormers: From Sparse View Planes to 3D Reconstruction
We present an approach for the planar surface reconstruction of a scene from images with limited overlap.
FWD: Real-time Novel View Synthesis with Forward Warping and Depth
Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications.
Understanding 3D Object Articulation in Internet Videos
We propose to investigate detecting and characterizing the 3D planar articulation of objects from ordinary videos.
PixelSynth: Generating a 3D-Consistent Experience from a Single Image
Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image.
Full-Body Awareness from Partial Observations
There has been great progress in human 3D mesh recovery and great interest in learning about the world from consumer video data.
