Loading video...

Video Failed to Load

Go Home

Checkout ObjectForesight! We tackle the problem of predicting future 3D object trajectories given a past context, purely from human videos of everyday interactions! [1/n]

mangahomanga's profile picture

Homanga Bharadhwaj @ CVPR

3,037 subscribers

16,365 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

#ECCV24 We introduce Controllable Human-Object Interaction Synthesis (CHOIS) to generate interactions given text in a 3D scene. w alex, Roozbeh Mottaghi Jiajun Wu Xavier Puig Karen. code: project page:
0:14

#ECCV24 We introduce Controllable Human-Object Interaction Synthesis (CHOIS) to generate interactions given text in a 3D scene. w alex, Roozbeh Mottaghi Jiajun Wu Xavier Puig Karen. code: project page:

Jiaman Li

13,185 views • 1 year ago

We recently obtained the highest-resolution 3D images of the human brain ever taken from outside the skull. This is the first look. Introducing Aleph, a research lab building brain interfaces for the telepathic future. (1/n)
0:13

We recently obtained the highest-resolution 3D images of the human brain ever taken from outside the skull. This is the first look. Introducing Aleph, a research lab building brain interfaces for the telepathic future. (1/n)

Aleph

1,354,575 views • 1 day ago

we open sourced the code to transform human videos into robot trajectories, so you can train robots with your hands 👐🏻 we used it in our recent paper R+X: Retrieval and Execution from Everyday Human Videos (ICRA 2025 🇺🇸) link and details in thread 🧵
0:11

we open sourced the code to transform human videos into robot trajectories, so you can train robots with your hands 👐🏻 we used it in our recent paper R+X: Retrieval and Execution from Everyday Human Videos (ICRA 2025 🇺🇸) link and details in thread 🧵

Norman Di Palo

10,578 views • 1 year ago

If you’re not in freefall, you’re likely contacting something. Yet 3D human-object interaction (HOI) reconstruction remains underexplored. PICO (#CVPR2025) recovers humans 🏃‍♂️, objects 🏓, and their interactions 👉🍎- all in 3D, from just a single internet image. 1/11
0:12

If you’re not in freefall, you’re likely contacting something. Yet 3D human-object interaction (HOI) reconstruction remains underexplored. PICO (#CVPR2025) recovers humans 🏃‍♂️, objects 🏓, and their interactions 👉🍎- all in 3D, from just a single internet image. 1/11

Shashank Tripathi

24,114 views • 1 year ago

Humans are social creatures and physical interaction with other humans plays an important role in our everyday life. In this thread, we explain how such interactions can be reconstructed in 3D from a single image utilising a denoising diffusion probabilistic model. (1/n)
0:10

Humans are social creatures and physical interaction with other humans plays an important role in our everyday life. In this thread, we explain how such interactions can be reconstructed in 3D from a single image utilising a denoising diffusion probabilistic model. (1/n)

Lea Wilken/Müller

76,538 views • 2 years ago

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3
0:12

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

Gordon Wetzstein

34,796 views • 1 year ago

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.
0:10

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

MrNeRF

24,729 views • 11 months ago

😇 Announcing Human, a global decentralized ID registry of all humanity With the core principle of 1 human = 1 account, we solve the problem of knowing if someone online is a real person, bot, or AI. Read more about our Alpha testing below 🧵
0:12

😇 Announcing Human, a global decentralized ID registry of all humanity With the core principle of 1 human = 1 account, we solve the problem of knowing if someone online is a real person, bot, or AI. Read more about our Alpha testing below 🧵

mainnet soon

460,238 views • 2 years ago

How do we create realistic models of dressed humans directly from visual data? We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos. Page: (1/6)
0:17

How do we create realistic models of dressed humans directly from visual data? We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos. Page: (1/6)

Qingqing Zhao

66,960 views • 2 years ago

Fit-up of bent or warped material is one of the most challenging aspects of autonomous shipbuilding. This lil’ snippet from an upcoming video shows how we’re solving that problem. The future of shipbuilding will look very different from the past.
0:17

Fit-up of bent or warped material is one of the most challenging aspects of autonomous shipbuilding. This lil’ snippet from an upcoming video shows how we’re solving that problem. The future of shipbuilding will look very different from the past.

Dustin Walper

55,697 views • 1 month ago

Introducing “FlowCam: Training Generalizable 3D Radiance Fields w/o Camera Poses via Pixel-Aligned Scene Flow”! We train a generalizable 3D scene representation self-supervised on datasets of raw videos, without any pre-computed camera poses or SFM! 1/n
0:12

Introducing “FlowCam: Training Generalizable 3D Radiance Fields w/o Camera Poses via Pixel-Aligned Scene Flow”! We train a generalizable 3D scene representation self-supervised on datasets of raw videos, without any pre-computed camera poses or SFM! 1/n

Vincent Sitzmann

88,503 views • 3 years ago

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0
0:11

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Moonlake

14,439 views • 6 months ago

Out of Context Human Race a friendly reminder
0:11

Out of Context Human Race a friendly reminder

Lovnesh

371,723 views • 2 years ago

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵
0:19

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Google DeepMind

1,467,183 views • 2 years ago

From a recent conversation with the great Kevin DeAnna (Kevin DeAnna) as part of his program Identity Politcs. We must build a future as glorious as our past.
0:18

From a recent conversation with the great Kevin DeAnna (Kevin DeAnna) as part of his program Identity Politcs. We must build a future as glorious as our past.

Jared Taylor

19,795 views • 2 months ago

Is this an IQ problem?? whats the point of this tackle from Gusto when you already leading by 3 goals?..
0:19

Is this an IQ problem?? whats the point of this tackle from Gusto when you already leading by 3 goals?..

𝚁𝙰𝚈 

68,703 views • 8 months ago

(1/2) MonoNPHM will be presented as a #CVPR2024 Highlight! Our Neural Parametric Head Model parametrizes both geometry and appearance. With the learned model, we can then 3D reconstruct and track human heads from images or videos.
0:18

(1/2) MonoNPHM will be presented as a #CVPR2024 Highlight! Our Neural Parametric Head Model parametrizes both geometry and appearance. With the learned model, we can then 3D reconstruct and track human heads from images or videos.

Matthias Niessner

17,209 views • 2 years ago

the future is predicting the future
0:14

the future is predicting the future

mass

139,588 views • 4 months ago

Thread of beautiful things from the past 🧵 1. A stunning drinks cabinet from the 1930s
0:12

Thread of beautiful things from the past 🧵 1. A stunning drinks cabinet from the 1930s

James Lucas

636,518 views • 9 months ago

SpatialTracker Tracking Any 2D Pixels in 3D Space Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain.
0:11

SpatialTracker Tracking Any 2D Pixels in 3D Space Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain.

AK

77,162 views • 2 years ago