Siddharth Katageri

Currently MS by Research @iiit_hyderabad.
Working on 3D Vision, Human-Scene Interaction.

[Charu Sharma @sh_charu]

2/2 papers accepted at WACV 2025!

1. "Towards a Training Free Approach for 3D Scene Editing" (accepted in second round)
2. "Adversarial Learning based Knowledge Distillation on 3D Point Clouds" (accepted in first round)

[Shaozhe Hao @haoshaozhe]

Can conditional generative models achieve strong visual representations, inherently?

We introduce BiGR, a conditional image generation model that unifies generative and discriminative tasks.

Project: https://t.co/h61iy9pDrH
Paper: https://t.co/qz6QxVyOnW

@kaihan_vis @haozsh

[Manu Gaur @gaur_manu]

🚨 Introducing Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation.

Given an image pair, it is easier for an MLLM to identify fine-grained visual differences during VQA evaluation than to independently detect and describe such differences 🧵(1/n):

[Kai Han @kaihan_x]

📢📢📢Introducing ConceptExpress for unsupervised
concept extraction from a single image. #ECCV2024
📖https://t.co/YwwmnMf4Bi
🌐https://t.co/iAaEAnMvvp
🧑‍💻https://t.co/ezf2zfE4tq
@haoshaozhe

[Astitva Srivastava @sarcastitva]

Excited to announce that "WordRobe" is accepted ✅ at #ECCV2024 (@eccvconf )
🚀🚀🚀🚀🚀

[Siddharth Katageri @siddKatageri]

3DVSS is back!! Eagerly waiting to attend and meet some of the greatest minds.

[3D Vision Summer School 2024 @3dvisionssindia]

Announcing 3D Vision Summer School 2024 to be held at IIIT Bangalore this year from 26May-1June. Offers a weeklong deep dive into 3D computer vision, Human Modelling, Rendering, Point Clouds, Meshes, 3D Generative AI & Animation with hands-on exp. #IIITH
https://t.co/g7EkRjrL0Z

[Astitva Srivastava @sarcastitva]

Get ready for the highest quality primer on 3D Computer Vision from some of the greatest minds!
🚀 🚀 🚀
Register Now! ⏰️

P.S. I'll be taking few hands-on sessions. 🙌🏻

[Makarand Tapaswi @MakarandTapaswi]

📢Happy to announce two #CVPR2024 papers from our Katha AI group @iiit_hyderabad! 🎉🎞️🔥

1. On 📺TV episode story summarization using recaps with @rodosingh23, @sridhruv.
2. On identity-aware video captioning with @HRaajesh, @dnaveenr, @zeeshank95.

Paper 🧵and arXiv soon. 1/4

[Siddharth Katageri @siddKatageri]

@anvekar_tejas thank you!!

[Siddharth Katageri @siddKatageri]

(2/2)
Contrastive learning (CL) and optimal transport (OT) are designed to complement each other synergistically. CL establishes coarse class clusters in both source and target domains individually, while OT aligns classes across domains.

[Siddharth Katageri @siddKatageri]

(1/2)
📢Our paper "Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation" was invited for an Oral presentation at #WACV2024!

webpage: https://t.co/JyZ0GgdLdW
arxiv: https://t.co/a7R7JcIwVo
video: https://t.co/eAzGhiadqy

[Siddharth Katageri @siddKatageri]

@wacv_official Yes, was finally able to upload!

[ISRO @isro]

Chandrayaan-3 Mission:
'India🇮🇳,
I reached my destination
and you too!'
: Chandrayaan-3

Chandrayaan-3 has successfully
soft-landed on the moon 🌖!.

Congratulations, India🇮🇳!

#Chandrayaan_3
#Ch3

[Siddharth Katageri @siddKatageri]

@wacv_official @xieqian26 Thanks for the update!
In my CMT the paper status and meta-reviews say accept, however, I haven't received an official mail of acceptance. Is this a cause for concern?

[Siddharth Katageri @siddKatageri]

Overjoyed to share that our paper titled "Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation" has been accepted at #WACV2024!!
More details coming soon...

[Charu Sharma @sh_charu]

1/1 paper accepted @siddKatageri @tdchaitanya @ArkadiptaDe

[Srinath Sridhar @drsrinathsridha]

Neural fields are emerging as useful signal representations in computer vision & beyond. Our full-day introductory @CVPR tutorial on the topic is now public.

Video: https://t.co/e1EaySsOaI
Slides: https://t.co/AmTCAzIAO1
Web: https://t.co/zZAJwBNs7W

[Jun Gao @JunGao33210520]

Excited to share our #NeurIPS2022 @NVIDIAAI work GET3D, a generative model that directly produces explicit textured 3D meshes with complex topology, rich geometric details, and high fidelity textures. #3D

Project page: https://t.co/LEkj9eqG69

[Mirela Ben-Chen @mirelaben]

As the fall semester is starting, this is the bi-yearly reminder of the collections of courses and seminars on geometry processing available here:
https://t.co/0ri7XYumuD
Ping me if you teach geometry processing / have a public zoom seminar and want your course / seminar added.