AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, László A. Jeni, Fernando De la Torre

TPAMI 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 34 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
add self-supervision loss to baseline network (ablation)Ba · 3DPW (32x32)MPJPE: 143.63 -> 128.88Improved
add self-supervision loss to resolution-aware network (ablation)RA · 3DPW (32x32)MPJPE: 135.29 -> 124.23Improved
replace baseline network with resolution-aware network (basic loss) (ablation)Ba · 3DPW (32x32)MPJPE: 143.63 -> 135.29Improved
add contrastive feature loss on top of RA+SS (ablation)RA+SS · 3DPW (32x32)MPJPE: 124.23 -> 117.12Improved
use MSE feature loss instead of contrastive loss (ablation)RA+SS · 3DPW (32x32)MPJPE: 117.12 -> 124.85Hurt
use cosine distance instead of full contrastive loss (ablation)RA+SS · 3DPW (32x32)MPJPE: 117.12 -> 125.08Hurt
add progressive training (ablation)RSC-Net · 3DPW (32x32)MPJPE: 127.05 -> 117.12Improved
use original symmetric self-supervision instead of directional loss (ablation)RSC-Net · 3DPW (32x32)MPJPE: 117.12 -> 156.25Hurt
use hierarchical supervision from all higher resolutions instead of only the highest (ablation)RSC-Net · 3DPW (32x32)MPJPE: 122.01 -> 117.12Improved
add global context module and upsampling layer to texture network (ablation)Texture network · Market-1501ReID loss: 60.21 -> 59.89Improved
fuse global features by concatenation instead of summation (ablation)Texture network · Market-1501ReID loss: 59.89 -> 60.25Hurt
add temporal recurrent module to single-frame modelRSC-Net · 3DPW video (32x32)MPJPE: 141.87 -> 123.14Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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