Search Results for author:
Found 10 papers, 3 papers with code
AGORA: Avatars in Geography Optimized for Regression Analysis
Additionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
DECO: Dense Estimation of 3D Human-Scene Contact In The Wild
In contrast, we focus on inferring dense, 3D contact between the full body surface and objects in arbitrary images.
Ranked #2 on
Contact Detection
on BEHAVE
PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation
Finally, both the teacher and the student networks are jointly fine-tuned in an end-to-end manner using temporal, self-consistency and adversarial losses, improving the accuracy of each individual network.
Ranked #70 on
3D Human Pose Estimation
on MPI-INF-3DHP
(using extra training data)
Learning to Generate Synthetic Data via Compositing
The synthesizer and target networks are trained in an adversarial manner wherein each network is updated with a goal to outdo the other.
Occluded Human Mesh Recovery
Along with the input image, we condition the top-down model on spatial context from the image in the form of body-center heatmaps.
Ranked #64 on
3D Human Pose Estimation
on 3DPW
(using extra training data)
PERI: Part Aware Emotion Recognition In The Wild
To address this, in the wild emotion recognition exploits full-body person crops as well as the surrounding scene context.
MIME: Human-Aware 3D Scene Generation
We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement.
Ranked #2 on
Indoor Scene Synthesis
on PRO-teXt
2D Semantic Segmentation task 1 (8 classes)
3D Semantic Scene Completion
+2
3D Human Pose Estimation via Intuitive Physics
Inspired by biomechanics, we infer the pressure heatmap on the body, the Center of Pressure (CoP) from the heatmap, and the SMPL body's Center of Mass (CoM).
Ranked #1 on
3D Human Pose Estimation
on RICH
BITE: Beyond Priors for Improved Three-D Dog Pose Estimation
To that end, we exploit contact with the ground as a form of side information.
Emotional Speech-Driven Animation with Content-Emotion Disentanglement
While the best recent methods generate 3D animations that are synchronized with the input audio, they largely ignore the impact of emotions on facial expressions.
