We just wrapped up Day 1 of ECCV 2024 Redux. If you missed it or want to revisit it, here’s a recap! In this blog post you’ll find the playback recordings, highlights from the presentations and Q&A, as well as the upcoming Meetup schedule so that you can join us at a future event.
Fast and Photo-realistic Novel View Synthesis from Sparse Images
Novel view synthesis generates new perspectives of a scene from a set of 2D images, enabling 3D applications like VR/AR, robotics, and autonomous driving. Current state-of-the-art methods produce high-fidelity results but require a lot of images, while sparse-view approaches often suffer from artifacts or slow inference. In this talk, I will present my research work focused on developing fast and photorealistic novel view synthesis techniques capable of handling extremely sparse input views.
ECCV 2024 Paper: CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians
Speaker: Avinash Paliwal is a PhD Candidate in the Aggie Graphics Group at Texas A&M University. His research is focused on 3D Computer Vision and Computational Photography.
Q&A
In your monocular image with the dog in the doorway example- how does your technique infer that the front edge of the rug continues straight when “revealed” from the novel view perspective? Does it learn that from your MLP’s training dataset?
Can you give us a sense of how much computation time is required?
Do you use image pyramids for depth resolution?
Is the depth derived from a Neuronal Network (Depth guessing)?
Robust Calibration of Large Vision-Language Adapters
We empirically demonstrate that popular CLIP adaptation approaches, such as Adapters, Prompt Learning, and Test-Time Adaptation, substantially degrade the calibration capabilities of the zero-shot baseline in the presence of distributional drift. We identify the increase in logit ranges as the underlying cause of miscalibration of CLIP adaptation methods, contrasting with previous work on calibrating fully-supervised models. Motivated by these observations, we present a simple and model-agnostic solution to mitigate miscalibration, by scaling the logit range of each sample to its zero-shot prediction logits
ECCV 2024 Paper: Robust Calibration of Large Vision-Language Adapters
Speaker: Balamurali Murugesan is currently pursuing his Ph.D. in developing reliable deep learning models. Earlier, he completed his master’s thesis on accelerating MRI reconstruction. He has published 25+ research articles in renowned venues.
Tree-of-Life Meets AI: Knowledge-guided Generative Models for Understanding Species Evolution
A central challenge in biology is understanding how organisms evolve and adapt to their environment, acquiring variations in observable traits across the tree of life. However, measuring these traits is often subjective and labor-intensive, making trait discovery a highly label-scarce problem. With the advent of large-scale biological image repositories and advances in generative modeling, there is now an opportunity to accelerate the discovery of evolutionary traits. This talk focuses on using generative models to visualize evolutionary changes directly from images without relying on trait labels.
ECCV 2024 Paper: Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution
Speaker: Mridul Khurana is a PhD student at Virginia Tech and a researcher with the NSF Imageomics Institute. His research focuses on AI4Science, leveraging multimodal generative modeling to drive discoveries across scientific domains.
Q&A
- What if you performed a selective sequencing of dna of each of the current species, then used that as the description of the bird’s image, for instance? Might that allow you to see the effects of historical changes in dna on the features of the animal’s image, by feeding those novel sequences to the model?
What’s Next at ECCV 2024 Redux?
Missed Day 1 at ECCV 2024 Redux? Register for the Zoom here for Day 3 and Day 4 events.
𝗗𝗮𝘆 𝟯: 𝗡𝗼𝘃𝗲𝗺𝗯𝗲𝗿 𝟮𝟭
Closing the Gap Between Satellite and Street-View Imagery Using Generative Models by Ningli Xu from The Ohio State University
High-Efficiency 3D Scene Compression Using Self-Organizing Gaussians by Wieland Morgenstern from Fraunhofer Heinrich Hertz Institute HHI
Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures by Maximilian R. and Yannick Kirchhoff from Medical Image Computing (MIC) @DKFZ German Cancer Research Center
𝗗𝗮𝘆 𝟰: 𝗡𝗼𝘃𝗲𝗺𝗯𝗲𝗿 𝟮𝟮
Zero-shot Video Anomaly Detection: Leveraging Large Language Models for Rule-Based Reasoning by Yuchen Yang from Johns Hopkins Whiting School of Engineering
Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models by Xiaoyu Zhu from Carnegie Mellon University
Dive into the groundbreaking research, all from the comfort of your own space.
You can find a complete schedule of upcoming Meetups on the Voxel51 Events page.
Get Involved!
There are a lot of ways to get involved in the Computer Vision Meetups. Reach out if you identify with any of these:
- You’d like to speak at an upcoming Meetup
- You have a physical meeting space in one of the Meetup locations and would like to make it available for a Meetup
- You’d like to co-organize a Meetup
- You’d like to co-sponsor a Meetup
Reach out to Meetup co-organizer Jimmy Guerrero on Meetup.com or ping me over LinkedIn to discuss how to get you plugged in.
—
These Meetups are sponsored by Voxel51, the company behind the open source FiftyOne computer vision toolset. FiftyOne enables data science teams to improve the performance of their computer vision models by helping them curate high quality datasets, evaluate models, find mistakes, visualize embeddings, and get to production faster. It’s easy to get started, in just a few minutes.
Top comments (0)