The image showcases an academic poster presentation titled "BiDiff: Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors." The researchers listed are Lihe Ding, Shaocong Dong, Zhangpeng Huang, Zibin Wang, Yiyuan Zhang, Kaixong Gong, Dan Xu, and Tianfan Xue.

Key elements of the poster include:
- **Motivation of the Bidirectional Diffusion (BiDiff):** This section highlights the advantages of both 2D and 3D image diffusions. It explains that 2D image diffusion offers better texture and diversity, while 3D shape diffusion provides superior consistency and geometry. The combined approach leverages priors from pre-trained foundation 2D and 3D models and utilizes bidirectional guidance to synchronize 2D & 3D denoise directions.
  
- **Bidirectional Diffusion (BiDiff) Framework:** The framework description outlines the process, where intermediate outputs from the 3D diffusion are rendered into 2D images to guide the denoising of the 2D diffusion model. The 2D outputs are re-projected to assist in 3D denoising, and BiDiff sampling outcomes serve as a starting point for optimization methods.

- **Examples and Results:** Various sections demonstrate what BiDiff can achieve, including generating diverse 3D objects and allowing user selection for further refinement. Final results show detailed geometry and texture in 3D objects such as complex creatures, buildings, and shoes. Another section breaks down texture and geometry control separately, showcasing the original and decoupled outputs side-by-side.

- **Visual Details:** The poster contains numerous visual elements like diagrams, charts, and sample images that explain the concepts and results. There is a small can of soda visible at the bottom left corner, indicating the informal, real-world environment of the presentation.

The poster emphasizes the efficacy of combining 2D and 3D priors in generating high-quality, intricate 3D models, showcasing a novel approach in the field of computer graphics and AI.
Text transcribed from the image:
•
UU
商汤
sensetime
BiDiff: Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
Lihe Ding*, Shaocong Dong*, Zhanpeng Huang, Zibin Wang, Yiyuan Zhang, Kaixiong Gong, Dan Xu, Tianfan Xue
Motivation of the Bidirectional Diffusion (BiDiff)
2D image diffusion has better texture and is more diverse.
3D shape diffusion has better 3D consistency and geometry.
Leverage priors from pre-trained foundation 2D & 3D models.
Bidirectional guidance to synchronize 2D&3D denoise direction.
bear
What can BiDiff do?
dancing
A bear dancing kick
dance
A bear dancing ballet
Random seed
27
Final results with detailed geometry and texture
Noise
2D diffusion model
2D
Denoising
11
Birdirectional
Guidance
Noise
3D diffusion model
3D
Denoising
step=960 step 920 step=800 step-500
A bear dressed as a lumberjack
step-200 step=0
feedforward results (40s)
*
refined results (20min)
texture mesh
(i) Efficiently generate diverse 3D objects in 40 seconds.
(ii) Users choose the favorite one for further refinement.
A car made out of pizza
Bidirectional Diffusion (BiDiff) framework
(a) we render the 3D diffusion's intermediate outputs into 2D images, which then
guide the denoising of the 2D diffusion model. Simultaneously, the intermediate
multi-view outputs from the 2D diffusion are re-projected to assist 3D denoising.
(b) BiDiff sampling outcomes as a strong starting point for optimization methods.
A silver platter piled high with fruits.
Allama wearing a suit
(a)
3D Noise
2D Noise
580
step t+1
step t
step t-1
...
3D Pipeline
3D Denoising
Noisy Input
3D Foundation
°
2D-3D Control
Model
3D SDF
Volume
Feature Volume
Rendering
(t-1 step)
2D Pipeline
Volume
Encoding
(b)
step 0
A llama wearing a suit.
An orangutan playing accordion with its hands spread wide.
3D-2D Control
A pig wearing a backpack
Feature Volume
Noisy Input
sos loss
2D Denoising
Multi-view images
(t-1 step)
An eagle head.
A Van Gogh style cabin
A GUNDAM robot
A Nike sport shoe
Decouple Texture and Geometry Control
An ancient Chinese
A golden skull.
A crystal skull
An ancient Gothic
tower.
A strong
A strong muscular
A blue and white
A blue and white
porcelain teapot
porcelain burger.
A blut and red
Superman clothes
A bule and red
Superman clothes
style car
A tetral with van
A house in van
Cogh's stamy sky
style painting on it
cegh starry sky
style
•Red Metal Golden
A (*) Dog.
Astronaut Astronaut Astronaut
(*) in weste
2D Diffusion Sampling
(40s)
3D Diffusion Sampling
(40%)
Refinement
Share 3D Feature Volume
Yo -15 Y 7.5
(20min)