AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Non-Rigid Structure-From-Motion: A Sequence-to-Sequence Translation Perspective

Hui Deng, Tong Zhang, Yuchao Dai, Jiawei Shi, Yiran Zhong, Hongdong Li

TPAMI 2024 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 14 citations (OpenAlex)

Read the paperCheck 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 changedWhereMeasuredEffect
use whole input sequence instead of single frame (ablation)sequence-to-sequence NRSfM · Human3.6M (GT 2D)MPJPE: 90.7 -> 72.5Improved
add nuclear norm low-rank loss (ablation)sequence-to-sequence NRSfM · Human3.6M (GT 2D)MPJPE: 81.1 -> 72.5Improved
add canonicalization loss (ablation)sequence-to-sequence NRSfM · Human3.6M (GT 2D)MPJPE: 98.1 -> 72.5Improved
add smoothness loss with absolute temporal encoding (ablation)sequence-to-sequence NRSfM · Human3.6M (GT 2D)MPJPE: 79.8 -> 72.5Improved
use four-layer transformer instead of single-attention Context Layer (ablation)Context Layer · Human3.6M (GT 2D)MPJPE: 72.5 -> 93.6Hurt
shuffle frame order at inference (ablation)trained model · Human3.6M (GT 2D)MPJPE: 72.5 -> 83.7Hurt
reverse frame order at inference (ablation)trained model · Human3.6M (GT 2D)MPJPE: 72.5 -> 80.9Hurt
add smoothness loss without temporal encoding (ablation)Base+nopos · Human3.6M, train length 32, inference length 32MPJPE: 78.3 -> 108.9Hurt
replace absolute encoding with no encoding for longer inference (ablation)Base+abspos · Human3.6M, inference length 512MPJPE: 204.8 -> 77.1Improved
use ALIBI instead of RoPE encoding (ablation)Base+rope · Human3.6M, inference length 512MPJPE: 90.9 -> 78.7Improved
add independent re-projection loss to the shape/motion predictor (ablation)full model · Human3.6M (GT 2D)MPJPE: 72.5 -> 89.8Hurt
freeze pre-trained shape/motion predictor (ablation)full model · Human3.6M (GT 2D)MPJPE: 72.5 -> 91.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy