🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Glad to share our work LIIF, has been accepted as #CVPR2021 Oral. We learn to generate images in a continuous representation, which can be presented in an arbitrary resolution (extrapolate to ×30). video & code: yinboc.github.io/liif/

How about 3D pre-training for motor control? We use Video Autoencoder to learn *3D* self-supervised representations from large-scale videos for RL. yanjieze.com/3d4rl Such 3D representations learn faster and transfer better sim-to-real than 2D pre-training such as MoCo.

🏗️ Policy Adaptation from Foundation Model Feedback #CVPR2023 geyuying.github.io/PAFF/ Instead of using foundation model as a pre-trained encoder (generator), we use it as a Teacher (discriminator) to tell where our policy did wrong and helps it adapts to new envs and tasks.

The robot climbs stairs🏯, steps over stones 🪨, and runs in the wild🏞️, all in one policy, without any remote control! Our #CVPR2023 Highlight paper achieves this by using RL + a 3D Neural Volumetric Memory (NVM) trained with view synthesis! rchalyang.github.io/NVM/

Want to obtain time-consistent dynamic mesh from monocular videos? Introducing: Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Monocular Videos liuisabella.com/DG-Mesh/ We reconstruct meshes with flexible topology change and build the corresp. across meshes. 🧵(1/n)

 🤖Introducing 📺𝗢𝗽𝗲𝗻-𝗧𝗲𝗹𝗲𝗩𝗶𝘀𝗶𝗼𝗻: a web-based teleoperation software!  🌐Open source, cross-platform (VisionPro & Quest) with real-time stereo vision feedback.  🕹️Easy-to-use hand, wrist, head pose streaming. Code: github.com/OpenTeleVision…

We introduce🌟Editable Image Elements🥳, a new disentangled and controllable latent space for diffusion models, that allows for various image editing operations (e.g., move, resize,  de-occlusion, object removal, variations, composition) jitengmu.github.io/Editable_Image… More details🧵👇

🌟Introducing "🤖SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model" anjiecheng.me/SpatialRGPT SpatialRGPT is a powerful region-level VLM that can understand both 2D and 3D spatial arrangements. It can process any region proposal (e.g., boxes or masks) and provide

Do we need separate models for image editing and conditional generation? We introduce🌟EditAR, a unified autoregressive model for diverse tasks, e.g., image editing, depth-to-image, edge-to-image, segmentation-to-image. jitengmu.github.io/EditAR/ More details🧵👇

Introducing Consistent Flow Distillation, a method with new theoretical perspective for text-to-3D generation: runjie-yan.github.io/cfd/ It is as simple and efficient as SDS, while having significantly better quality and diversity. The first author Runjie is applying for PhD 2025