thu-lyj-lab / t3bench Goto Github PK
View Code? Open in Web Editor NEWT3Bench: Benchmarking Current Progress in Text-to-3D Generation
Home Page: https://t3bench.com/
T3Bench: Benchmarking Current Progress in Text-to-3D Generation
Home Page: https://t3bench.com/
Hello, thank you for providing a comprehensive benchmark for 3D generation. I am the author of GaussianDreamer and I would like to know how to submit our results on T3bench. Here are our results.
Single Obj. | ** Single w/ Surr.** | Multi Obj. | Average |
---|---|---|---|
54.0 | 48.6 | 34.5 | 45.7 |
Wonderful work! I've been following this work for a while and I noticed that in your latest submission for ECCV 24, several recent work like MVDream, DreamGaussian, etc. are added in the leaderboard. I'm wondering that whether the mesh results of these newly added methods can be released like the last update in 2023/10/24. I'm planning to leverage these mesh results as part of my dataset. I'll be very appreciated for their release. Overall, T3Bench is truly a contributing work and wish your submission for ECCV be accepted ASAP.
Thanks again! And look forward to your reply.
Hello! Thank you for this fantastic work. Could you please provide the NeRF ckpt files corresponding to the released mesh results of all prompt sets and methods? I've noticed a significant drop in rendering quality after mesh extraction. I'm very interested in their results and would like to test and compare their performance.
When using pip install for requirement.txt, salesforce-lavis, and image-reward are in conflict when sharing the transformer. They have different requirements for the version of the transformer.
Hello, this is a wonderful job. I would like to know the generation time of these methods (ProlificDreamer, SJC, Fantasia3D, LatentNeRF, Magic3D, Dreamfusion) in the paper?
Would it be possible to also release the human annotations? Thanks!
Hello! Thanks for your interesting work. I have a question regarding the text prompts you release in this benchmark.
I am wondering if you are providing triplets of the increasingly descriptive text prompts for every object. or if every text prompt is referring to a random object.
For example:
If I get an average alignment score 3,
then the normalized score is 3/5x100 = 60
or (3-1)/4x100 = 50 ?
Currently based on your paper sec 4.2, I assume the second calculation is correct.
Is that right?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.