Seoyeon Stella Yang @codestella

AI Roboticist Girl 🙌💕 3d Vision / Diffusion / 3d generation / NeRF / Visual localization / Vision AI Phd candidate in Seoul National University @SNUnow👩‍💻 대한민국 서울 Joined February 2021

Tweets

588
Followers

681
Following

750
Likes

752

DailyPapers @HuggingPapers

9 months ago

Unlock precise 3D object editing with NANO3D! This training-free framework offers coherent, mask-free edits for game, animation, and robotics content. It even preserves unedited regions perfectly.

2 15 66 12K 35

View Details

AK @_akhaliq

a year ago

Bytedance presents EX-4D EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh

7 63 367 39K 176

View Details

Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction Abstract (excerpt): While dynamic Gaussian Splatting offers an efficient representation, vanilla models optimize all Gaussian primitives uniformly, ignoring whether they are well or poorly observed. This limitation leads to motion drifts under occlusion and degraded synthesis when extrapolating to unseen views. We argue that uncertainty matters: Gaussians with recurring observations across views and time act as reliable anchors to guide motion, whereas those with limited visibility are treated as less reliable. To this end, we introduce USplat4D, a novel Uncertainty-aware dynamic Gaussian Splatting framework that propagates reliable motion cues to enhance 4D reconstruction. Our key insight is to estimate time-varying per-Gaussian uncertainty and leverage it to construct a spatio-temporal graph for uncertainty-aware optimization.

1 8 78 5K 56

View Details

Wayve @wayve_ai

9 months ago

🔷 Introducing Rig3R - our new geometric foundation model for 3D perception in AVs. wayve.ai/thinking/rig3r/

3 83 523 40K 258

View Details

Tencent Hy @TencentHunyuan

9 months ago

Hunyuan's latest work: Generating high-quality 3D worlds in 5 seconds with a single GPU. 🔥 Code: github.com/imlixinyang/Fl… Page: imlixinyang.github.io/FlashWorld-Pro…

Tengfei Wang @DylanTFWang

9 months ago

⚡️Generating 3DGS scenes in 5 seconds on a single GPU⚡️ #FlashWorld enables ⚡️*fast*⚡️ (10~100x faster than previous methods) and 🔥*high-quality*🔥 3D world generation, from a single image or text prompt. Code: github.com/imlixinyang/Fl… Page: imlixinyang.github.io/FlashWorld-Pro…

18 117 750 120K 573

8 74 530 49K 263

View Details

ダックビル＠STUDIO DUCKBILL LLC @DuckbillStudio

10 months ago

Blenderアドオンの3DGSレンダーでリアルタイムレンダリングできるようになった。試してみよう。

Chris make some 3D scans @ChrisAtKIRI

10 months ago

We just open-sourced 3DGS render blender addon v4.0 (github.com/Kiri-Innovatio…)! It has been a while, but we are still updating this 3D Gaussian Splatting tool! In this version, we added a real-time rendering mode, so say goodbye to those laggy displays in the viewport! Here is an

7 134 1K 69K 682

0 42 356 25K 151

View Details

Sherwin Bahmani @sherwinbahmani

10 months ago

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: research.nvidia.com/labs/toronto-a… Code and Models: github.com/nv-tlabs/lyra Paper: arxiv.org/abs/2509.19296

20 67 257 67K 85

View Details

Min Choi @minchoi

10 months ago

This is wild. ByteDance just dropped Lynx. This AI can turn one photo of anyone into high quality videos with same face in multiple scenes, moods, and motion 10 wild examples + how to try it: 1. One photo → many videos

29 91 539 121K 598

View Details

DailyPapers @HuggingPapers

10 months ago

Metastone unveils MCP-AgentBench A new benchmark evaluating real-world language agent performance with MCP-mediated tools. It features 33 live servers & 188 tools to rigorously test agent capabilities beyond traditional metrics.

2 14 65 13K 37

View Details

AK @_akhaliq

10 months ago

two new Gemini 2.5 models Flash and Flash-Lite are now available in anycoder available as gemini-flash-latest and gemini-flash-lite-latest

2 3 32 25K 4

View Details

Tencent Hy @TencentHunyuan

10 months ago

🔥Excited to introduce Tencent Hunyuan3D-Omni, the industry's first 3D asset creation system with multi-condition control. Built on the open-source Hunyuan3D 2.1 as the "ControlNet of 3D," it addresses single-view occlusions, and poor geometry by integrating up to four control conditions. Two core innovations power the system: a Lightweight Unified Control Encoder for efficient multimodal fusion, and a Progressive Difficulty-Aware Training Strategy that boosts robustness. ✅Under single-image conditions, skeletal input provides precise pose control for animation and avatars. ✅Point cloud input—full or depth-projected—removes visual ambiguity and yields accurate photorealistic geometry. ✅Bounding box control adjusts L/W/H ratios to match design scale. ✅Voxel control sculpts topology for engineering and creative workflows. We are open-sourcing inference code and weights to accelerate controllable 3D research and industry deployment. Code: github.com/Tencent-Hunyua… Weights: huggingface.co/tencent/Hunyua… Tech Report: arxiv.org/pdf/2509.21245 #3DGenAI #TencentHunyuan #OpenSourceAI

11 85 496 35K 273

View Details

Tencent Hy @TencentHunyuan

10 months ago

We are introducing Hunyuan3D-Part: an open-source part-level 3D shape generation model that outperforms all existing open and close-source models. Highlights: 🔹P3-SAM: The industry's first native 3D part segmentation model. 🔹X-Part: A part generation model that achieves state-of-the-art results in controllability and shape quality. Key-features: 1️⃣Eliminates the use of 2D SAM during training, relying solely on a large-scale dataset with 3.7 million shapes and clean part annotations. 2️⃣Introduces a new automated segmentation pipeline in 3D without user intervention. 3️⃣Implements a diffusion-based part decomposition pipeline utilizing both geometry and semantic clues. Code: github.com/Tencent-Hunyua… Weights: huggingface.co/tencent/Hunyua… Tech reports: 🔸P3-SAM： → Paper: arxiv.org/abs/2509.06784 → Project page: murcherful.github.io/P3-SAM/ 🔸X-Part： → Paper: arxiv.org/abs/2509.08643 → Project page: yanxinhao.github.io/Projects/X-Par… Try it now： → (Light version) Hugging Face demo: huggingface.co/spaces/tencent… → (Full version) Hunyuan3D Studio: 3d.hunyuan.tencent.com/studio

23 156 917 73K 500

View Details

alphaXiv @askalphaxiv

10 months ago

Apple just proposed the first unified visual tokenizer! They proposed ATOKEN which is the first tokenizer that jointly cover images, videos, and 3D assets in a single shared 4D latent/token space, matching performance with any other specialized tokenizers.

10 78 485 39K 289

View Details

Kwang Moo Yi @kwangmoo_yi

10 months ago

Yang et al., "Dense Semantic Matching with VGGT Prior" Train a decoding head for semantic segmentation, with sparse GT supervision and cycle consistency --> dense non-rigid warping. Using a foundational model for "matching" for sure works better than "any" foundational model.

1 14 108 6K 71

View Details

Seoyeon Stella Yang @codestella

10 months ago

@EHuanglu Workflow

0 0 0 9 0

View Details

Emm | scenario.com @emmanuel_2m

a year ago

"Blender MCP" vs. "Generative 3D" – The Showdown ⚔️ Side-by-side comparison of two generated buildings: ⬅️ The 1st one (left) was created using Blender MCP (powered by Claude 3.7). ➡️ The 2nd one (right) was generated with a generative 3D model (direct 2D-to-3D). Check out the differences below 👇

62 144 1K 266K 1K

View Details

Ziwei Liu @liuziwei7

10 months ago

🤩4D World Model Open Sourced🤩 All the **𝐜𝐨𝐝𝐞, 𝐦𝐨𝐝𝐞𝐥 𝐚𝐧𝐝 𝐝𝐚𝐭𝐚** of #4DNeX have been publicly released: - Project: 4dnex.github.io - Code and Model: github.com/3DTopia/4DNeX - Data @huggingface: huggingface.co/datasets/3DTop…

AK @_akhaliq

11 months ago

4DNeX Feed-Forward 4D Generative Modeling Made Easy

2 15 66 64K 34

3 51 232 27K 136

View Details

Xin Kong @XinKong_IC

10 months ago

🚀 Excited to share CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis! Let’s recon 3D world generatively. CausNVS handles any number of input views, synthesizes novel views autoregressively, enables interactive streaming and flexible N-to-M NVS.

2 19 106 10K 58

View Details

Kwang Moo Yi @kwangmoo_yi

11 months ago

Dayani et al., "MV-RAG: Retrieval Augmented Multiview Diffusion" Retrieval augmentation for 3D recon with multi-view diffusion models. Trains both with 3D and 2D assets during training, and uses 2D natural images for inference. Makes sense, I guess? Many things look alike!