Search Results for author: Leonid Keselman

Found 9 papers, 5 papers with code

Flexible Techniques for Differentiable Rendering with 3D Gaussians

no code implementations28 Aug 2023 Leonid Keselman, Martial Hebert

Fast, reliable shape reconstruction is an essential ingredient in many computer vision applications.

Novel View Synthesis Optical Flow Estimation

Optimizing Algorithms From Pairwise User Preferences

no code implementations8 Aug 2023 Leonid Keselman, Katherine Shih, Martial Hebert, Aaron Steinfeld

Typical black-box optimization approaches in robotics focus on learning from metric scores.

Social Navigation

Shape from Shading for Robotic Manipulation

no code implementations24 Apr 2023 Arkadeep Narayan Chaudhury, Leonid Keselman, Christopher G. Atkeson

Controlling illumination can generate high quality information about object surface normals and depth discontinuities at a low computational cost.

Discovering Multiple Algorithm Configurations

no code implementations13 Mar 2023 Leonid Keselman, Martial Hebert

In this work, we extend algorithm configuration to automatically discover multiple modes in the tuning dataset.

Depth Estimation Motion Planning +1

Approximate Differentiable Rendering with Algebraic Surfaces

1 code implementation21 Jul 2022 Leonid Keselman, Martial Hebert

In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs.

Pose Estimation

Venue Analytics: A Simple Alternative to Citation-Based Metrics

1 code implementation29 Apr 2019 Leonid Keselman

We present a method for automatically organizing and evaluating the quality of different publishing venues in Computer Science.

Direct Fitting of Gaussian Mixture Models

1 code implementation11 Apr 2019 Leonid Keselman, Martial Hebert

Part of this work analyzes a general formulation for evaluating likelihood of geometric objects.

Dynamics Based 3D Skeletal Hand Tracking

1 code implementation22 May 2017 Stan Melax, Leonid Keselman, Sterling Orsten

Based on a depth sensor's samples, the system generates constraints that limit motion orthogonal to the rigid body model's surface.

3D Object Tracking Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.