Alexey Bokhovkin

Computer Vision researcher @ TUM
3D Indoor Understanding

[Alexey Bokhovkin @ABokhovkin]

📢SceneFactor code is released!
SceneFactor is a factored latent diffusion for controllable, large-scale scene synthesis and editing!

w/
@QTDSMQ, @shubhtuls, @angelaqdai

Check out the code here: https://t.co/FIMiRSTFIs. We present SceneFactor at #CVPR2025 on Fri 13, -10:30 PDT. Don't forget to drop by 😊

[Matthias Niessner @MattNiessner]

📢Animating the Uncaptured 📢

We animate 3D humanoid meshes using video diffusion priors given a text prompt.

🎥https://t.co/EpFW86gaRw
🌍https://t.co/suMQs8oQCL

Realistic motion generation for 3D characters - without motion capture! 🚀

Great work by @marcbenedi @angelaqdai

[Angela Dai @angelaqdai]

📢ExCap3D: Multilevel Captioning of Objects in 3D Scenes

@chandan__yes 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: https://t.co/6tWzlYsx5F
w/ @david_roz_

[Angela Dai @angelaqdai]

📢 ScanNet++ v2 Benchmark Release! 🏆

Test your state-of-the-art models on:
🔹 Novel View Synthesis 📸➡️🖼️
🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️
Shoutout to @chandan__yes and @liuyuehcheng for their incredible work👏

🚀Check it out: https://t.co/SKCGM23hA0

[Angela Dai @angelaqdai]

📢MeshArt: Generating Articulated Meshes with Structure-guided Transformers

@DaoyiGao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis.

w/ @yawarnihal @craigleili
Project: https://t.co/aZPVyn8kQd

[Angela Dai @angelaqdai]

Excited to announce ScanNet++ v2!🎉

@chandan__yes and @liuyuehcheng 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/ @MattNiessner
https://t.co/QayR1S8KZZ

[Matthias Niessner @MattNiessner]

📢📢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 smartphones.

Key idea: distill reconstruction constraints from a multi-view head diffusion model to complete unobserved regions.

https://t.co/prz5HnGoWq
https://t.co/XkWBKScwb2

Great work by @jiapeng_tang @davidedavoli @TobiasKirschst1 @liamschoneveld

[Angela Dai @angelaqdai]

📢DNF: Generating 4D animations with dictionary-based neural fields!

@xinyi092298 presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.

https://t.co/yAZi2k0PjB

[Alexey Bokhovkin @ABokhovkin]

I'm so excited to introduce SceneFactor!

[Angela Dai @angelaqdai]

📢SceneFactor: Generating & editing 3D indoor scenes from text!

@ABokhovkin presents a factored latent diffusion for controllable, large-scale scene synthesis -- decomposed into high-level semantic generation + geometric refinement

w/ @QTDSMQ, @shubhtuls
https://t.co/WGTw70cKIo

[Matthias Niessner @MattNiessner]

📢📢 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 audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc.

We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours.

Project: https://t.co/4TpbW3rn11
Video: https://t.co/WidbmXZtEY

Great work by @shivangi2201, @ASevastopolsky, @TobiasKirschst1, @JustusThies, @angelaqdai

[Angela Dai @angelaqdai]

How can we generate high-fidelity, complex 3D scenes?

@QTDSMQ's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis!

w/ @craigleili, @MattNiessner
https://t.co/wv9bIhkkYi

[Angela Dai @angelaqdai]

Excited to present DiffCAD coming to #SIGGRAPH2024!

@DaoyiGao introduces the first probabilistic single-view CAD retrieval & alignment.
We train only on synthetic -> generalize robustly to real images!
Check out the code: https://t.co/hBCoN0Hx3w

w/@david_roz_, @StefanLeuteneg1

[Angela Dai @angelaqdai]

Excited to present GenZI at #CVPR2024!

@craigleili 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!
https://t.co/hUhMgUoU70
https://t.co/rnn1G5HOuu

[Alexey Artemov @artonson]

AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans

A method for unsupervised instance segmentation of 3D outdoor LiDAR scenes.

Project: https://t.co/m8DJanWH2T
Vid: https://t.co/Z9OyZbskdJ
Paper : https://t.co/rrmvQdjmWV

[Alexey Bokhovkin @ABokhovkin]

@artonson Really nice work, congrats!

[Angela Dai @angelaqdai]

Check out our #CVPR'24 papers on 3D human interactions, generative 3D modeling, and uncertainty-aware and unsupervised 3D semantic scene understanding!

Congrats to @craigleili @david_roz_ @chrdiller @yawarnihal @shivangi2201 @jiapeng_tang @AnhQuanCAO for their amazing work!

[Angela Dai @angelaqdai]

Check out @chrdiller'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.

https://t.co/Cl5Jw9oFBO
https://t.co/FVIFqEpjHi

[Alexey Bokhovkin @ABokhovkin]

@KatyaArtemov @TolokaAI Super cool! My warmest congratulations!

[Matthias Niessner @MattNiessner]

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.

https://t.co/FqaqF7tMPM