anyeZHY/tesseract

Model

We propose TesserAct, the 4D Embodied World Model, which takes input images and text instruction to generate RGB, depth,

6 commits

1 linked in READMEs

updated May 1, 2025

See the code

README

TesserAct: Learning 4D Embodied World Models

Haoyu Zhen*, Qiao Sun*, Hongxin Zhang, Junyan Li, Siyuan Zhou, Yilun Du, Chuang Gan

Paper PDF | Project Page | Model on Hugging Face | Code

We propose TesserAct, the 4D Embodied World Model, which takes input images and text instruction to generate RGB, depth, and normal videos, reconstructing a 4D scene and predicting actions.

diffusers

image-to-video

safetensors

Contributors

anyeZHY

5 commits

nielsr

1 commits

Similar repos

AetherWorldModel/AetherV1

Model

Aether: Geometric-Aware Unified World Modeling

UMass-Embodied-AGI/TesserAct

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

408

gzzyyxy/orv-gen-model

Model

This repository contains the model described in [ORV: 4D Occupancy-centric Robot Video…

shiyi0408/FlexiAct

Model

FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios

TencentARC/VerseCrafter

Model

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

facebook/ActionMesh

Space

```

114

Yabo/FramePainter

Model

This repository contains the model described in [FramePainter: Endowing Interactive Image Editing…

GSAI-ML/FlexWorld

Model

This model performs image-to-video generation based on the paper [FlexWorld: Progressively…

Linked in READMEs

NTUMARS/Awesome-World-Model-for-Robotics-Policy

811

README badge

anyeZHY/tesseract

Model

We propose TesserAct, the 4D Embodied World Model, which takes input images and text instruction to generate RGB, depth,

6 commits

1 linked in READMEs

updated May 1, 2025

See the code

README

TesserAct: Learning 4D Embodied World Models

Haoyu Zhen*, Qiao Sun*, Hongxin Zhang, Junyan Li, Siyuan Zhou, Yilun Du, Chuang Gan

Paper PDF | Project Page | Model on Hugging Face | Code

We propose TesserAct, the 4D Embodied World Model, which takes input images and text instruction to generate RGB, depth, and normal videos, reconstructing a 4D scene and predicting actions.

diffusers

image-to-video

safetensors