Research map / 3D vision / Depth and stereo
DiffPoseNet: Direct Differentiable Camera Pose Estimation
Chethan M. Parameshwara, Gokul Hari, Cornelia Fermüller, Nitin J. Sanket, Yiannis Aloimonos
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Estimate normal flow directly rather than project optical flow onto image gradients | NFlowNet versus optical-flow baselines · TartanAir abandonedfactory and hospital sequences | PEE | Mixed |
| Use normal flow with a differentiable cheirality constraint for pose estimation | DiffPoseNet · TartanAir MH000-007 | ATE | Mixed |
| Use normal flow with cheirality rather than an epipolar layer with optical flow | DiffPoseNet versus BiLevelOpt and Cheirality-OF · Noisy motion fields | relative pose error | Improved |
| Train on TartanAir and evaluate on another dataset without fine-tuning or retraining | DiffPoseNet · TUM-RGBD | ATE | Mixed |
| Use a differentiable cheirality constraint rather than strong feature or photometric constraints | DiffPoseNet · Noisy motion fields | relative pose error | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- DeepTAM — DeepTAM: Deep Tracking and Mapping (ECCV 2018) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FMPose3D: monocular 3D pose estimation via flow matching (CVPR 2026 · similarity 0.88)
- DiffPose: Toward More Reliable 3D Pose Estimation (CVPR 2023 · similarity 0.87)
- DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion Models (ICCV 2023 · similarity 0.87)
- FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow (NeurIPS 2023 · similarity 0.86)
- Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion (CVPR 2021 · similarity 0.86)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
