Can we match visual features jointly across multiple frames? Yes! Barbara Roessle's #ICCV2023 paper proposes a differentiable pose optimization for end2end feature matching across multiple frames, thus obtaining better poses! barbararoessle.github.io/e2e_multi_view… youtu.be/uuLb6GfM9Cg

We've released the ScanNet++ data! Check it out: kaldir.vc.in.tum.de/scannetpp/ 280 high-fidelity 3D scenes w/ 1mm geometry, DSLR+iPhone images, semantics We're currently beta-testing, please bear with us - approval may initially take up to 2 weeks Test scenes and benchmark to come!

Diffusion models are awesome! Check out our survey on 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 𝐟𝐨𝐫 𝐕𝐢𝐬𝐮𝐚𝐥 𝐂𝐨𝐦𝐩𝐮𝐭𝐢𝐧𝐠! We give an introduction to diffusion models and highlight how they are used by state-of-the-art methods in graphics and vision. arxiv.org/abs/2310.07204

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference. cg-hoi.christian-diller.de youtube.com/watch?v=GNyQwT…

Check out our #CVPR'24 papers on 3D human interactions, generative 3D modeling, and uncertainty-aware and unsupervised 3D semantic scene understanding! Congrats to Lei Li David Rozenberszki Christian Diller Yawar Siddiqui Shivangi Jiapeng Tang Anh-Quan Cao for their amazing work!

AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans A method for unsupervised instance segmentation of 3D outdoor LiDAR scenes. Project: artonson.github.io/publications/2… Vid: youtube.com/watch?v=ioKJWY… Paper : arxiv.org/pdf/2403.16318…

Excited to present GenZI at #CVPR2024! Lei Li introduces GenZI, the first zero-shot approach to creating realistic 3D human-scene interactions by leveraging interaction priors from large VLMs. Code and data on our website! craigleili.github.io/projects/genzi/ youtu.be/ozfs6E0JIMY

Excited to present DiffCAD coming to #SIGGRAPH2024! Daoyi Gao introduces the first probabilistic single-view CAD retrieval & alignment. We train only on synthetic -> generalize robustly to real images! Check out the code: daoyig.github.io/DiffCAD_/ w/David Rozenberszki, Stefan Leutenegger

How can we generate high-fidelity, complex 3D scenes? Quan Meng's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ Lei Li, Matthias Niessner quan-meng.github.io/projects/lt3sd/

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an

I'm so excited to introduce SceneFactor!

📢DNF: Generating 4D animations with dictionary-based neural fields! Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency. xzhang-t.github.io/project/DNF/

📢📢𝐆𝐀𝐅: 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐀𝐯𝐚𝐭𝐚𝐫 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 𝐟𝐫𝐨𝐦 𝐌𝐨𝐧𝐨𝐜𝐮𝐥𝐚𝐫 𝐕𝐢𝐝𝐞𝐨𝐬 𝐯𝐢𝐚 𝐌𝐮𝐥𝐭𝐢-𝐯𝐢𝐞𝐰 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧📢📢 We reconstruct animatable Gaussian head avatars from monocular videos captured by commodity devices such as

📢MeshArt: Generating Articulated Meshes with Structure-guided Transformers Daoyi Gao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis. w/ Yawar Siddiqui Lei Li Project: daoyig.github.io/Mesh_Art/

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ Matthias Niessner kaldir.vc.in.tum.de/scannetpp

📢 ScanNet++ v2 Benchmark Release! 🏆 Test your state-of-the-art models on: 🔹 Novel View Synthesis 📸➡️🖼️ 🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️ Shoutout to Chandan Yeshwanth and Yueh-Cheng Liu for their incredible work👏 🚀Check it out: kaldir.vc.in.tum.de/scannetpp/

📢Animating the Uncaptured 📢 We animate 3D humanoid meshes using video diffusion priors given a text prompt. 🎥youtu.be/_YL1J_V3smI 🌍marcb.pro/atu Realistic motion generation for 3D characters - without motion capture! 🚀 Great work by Marc Benedí Angela Dai

📢ExCap3D: Multilevel Captioning of Objects in 3D Scenes Chandan Yeshwanth generates consistent object and part-level descriptions of objects in 3D scenes, and introduces a new dataset with 190k captions for 34k ScanNet++ objects. Project: cy94.github.io/excap3d w/ David Rozenberszki

📢SceneFactor code is released! SceneFactor is a factored latent diffusion for controllable, large-scale scene synthesis and editing! w/ Quan Meng, Shubham Tulsiani, Angela Dai Check out the code here: github.com/alexeybokhovki…. We present SceneFactor at #CVPR2025 on Fri 13, -10:30