HackerTube
HomeLongsLikedHistoryWatch laterCategoriesPlaylistsSettings

Dual Photography

mm6482304 HN recommenders · recommended in 4 months, 2013-2026
YouTube
24K views · 17 years ago · demo · evergreen

The SIGGRAPH 2005 demo of dual photography from Stanford, which swaps the roles of projector and camera to render a scene from the light's point of view. It includes the reveal of a hidden playing card.

Cited whenever threads discuss recovering hidden images or non-line-of-sight imaging, as a clear demonstration of light transport.

Computer graphics & renderingComputer vision, speech & NLP#dualphotography#lighttransport#siggraph#projectorcamera#imaging

10 comments from Hacker News

@janfoeh2026 · in “Image-blaster: Creates 3D environments, SFX, and meshes from a single image”

I've never forgotten this SIGGRAPH demo from almost twenty years ago, in which the authors effectively switch camera and light source computationally (... in a static scene) [1] Ever since then, I have viewed scenes such as the "lingerie store scene" from Enemy of the State [2] with a little bit less eye rolling... [1] - ▶ this video [2] - link

CitesView on HN
@rzzzt2021 · in “Non–line-of-sight imaging over 1.43km [pdf]”

I was immediately reminded of the Dual Photography paper (well, I had to look it up first; I only remembered the "photographing a playing card that is facing away" demo at the end): - link - ▶ this video

CitesView on HN
@saeranv2020 · in “In a photo of a black hole, a possible key to mysteries”

> Does anyone assert that any photon carries information about what it interacted with in the past? Does a photon have any information content other than its energy/wavelength? So "each one carries a bit of the image of whatever it hits" is total (ok, be nice now) poetic blarney. An analogy to how we perceive things seems appropriate. The light from some source (i.e the sun) hits an object, the light rays are then reflected/transmitted/refracted through the surface based on various material properties. Your eye, acting like a pinhole camera, captures all the light rays from that surface, and then projects it onto the sensor reception surface (I think the retina?) creating the 'image' that we see. So the specific way the light rays interacts with the surface is what creates the 'information content'. For example, we perceive a blue-colored surface because the surface properties (i.e roughness) will specifically reflect wavelengths associated with blue. A specular surface will reflect light back to the eye, creating a 'shiny' surface. A very cool demonstration of how light conveys information is in dual photography: ▶ this video And the original paper: link . They shine a light source onto an object, take a picture, and then by processing the light rays in the photo, are able to generate the same scene but from the perspective of the light source. It's really astounding when you see it. They can do this reconstruction because the flow of light rays from the light source to the obj

RecommendsView on HN
@pdkl952020 · in “TV Backlight Compensation”

It sounds like "Dual Photography". link "We present a novel photographic technique called dual photography, which exploits Helmholtz reciprocity to interchange the lights and cameras in a scene. With a video projector providing structured illumination, reciprocity permits us to generate pictures from the viewpoint of the projector, even though no camera was present at that location." I recommend watchign the video from the paper for good explains and demonstrates the technique. It's very impressive work. ▶ this video

RecommendsView on HN
@rzzzt2019 · in “Shadows used to peer around corners”

Reminds me of this work, aiming to "reverse" the light path between a projector and a camera/photosensor: ▶ this video

CitesView on HN
@evanb2017 · in “Turning Corners into Cameras: Principles and Methods”

This reminds me of dual photography, where one can recover hidden images from diffuse-diffuse light transfer. video: ▶ this video page: link

CitesView on HN
@evanb2015 · in “An Algorithm That Unscrambles Fractured Images”

This reminds me of dual photography: link in the sense that I imagine unscrambling the glittered image will be significantly easier if you can plug in known sources to the transfer matrix. Edit: the video there didn't work for me any more, here's the youtube link ▶ this video

CitesView on HN
@uptown2014 · in “Extracting audio from visual information”

Reminds me a little of "Dual Photography" as presented at Siggraph in 2005. All the data you need to construct a new view is available if you know where and how to look: ▶ this video

CitesView on HN
@uptown2014 · in “How taking pictures through windows can inadvertently reveal your location”

Dual Photography has always been the optical "trick" that's blown me away. Here's the demo video from Siggraph in 2005: ▶ this video Skip ahead to 4:19 for a succinct demo.

Strongly recommendsView on HN
@evanb2013 · in “Reflected hidden faces in photographs revealed in pupil”

This reminds me of dual photography [1], in which you trade many projectors and one camera for one projector and many cameras using time reversal symmetry. The video [2] gives a good explanation, and the revelation of the playing card is what strikes me as similar to revealing reflected hidden faces. [1] link [2] ▶ this video

RecommendsView on HN
3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 20135:51

3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013

Daniel CohenOr
2.3M views • 13 years ago
AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #2154:17

AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215

Two Minute Papers
65K views • 8 years ago
Eulerian Video Magnification4:28

Eulerian Video Magnification

Miki Rubinstein
788K views • 14 years ago
Marc Levoy - Lectures on Digital Photography - Lecture 1 (21mar16).mp41:15:21

Marc Levoy - Lectures on Digital Photography - Lecture 1 (21mar16).mp4

Marc Levoy
512K views • 10 years ago
Faking RTX Global Illumination vs. RTX | 100% Ray-Traced Game, Pt 127:27

Faking RTX Global Illumination vs. RTX | 100% Ray-Traced Game, Pt 1

Gamers Nexus
260K views • 7 years ago
ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition3:21

ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition

QiPanComputerVision
571K views • 17 years ago
Make Your Renders Unnecessarily Complicated5:25

Make Your Renders Unnecessarily Complicated

sirrandalot
1.2M views • 3 years ago
3D Gaussian Splatting! - Computerphile17:40

3D Gaussian Splatting! - Computerphile

Computerphile
273K views • 2 years ago
NVIDIA RTX Real-Time Ray Tracing Tech Demo From Remedy Entertainment1:46

NVIDIA RTX Real-Time Ray Tracing Tech Demo From Remedy Entertainment

NVIDIA GeForce
497K views • 8 years ago
Disney's Practical Guide to Path Tracing9:32

Disney's Practical Guide to Path Tracing

Walt Disney Animation Studios
914K views • 10 years ago
A Deep Dive into Nanite Virtualized Geometry1:10:00

A Deep Dive into Nanite Virtualized Geometry

SIGGRAPH Advances in Real-Time Rendering
278K views • 5 years ago
SYMBOLICS S-PACKAGES 3D GRAPHICS AND ANIMATION DEMO29:16

SYMBOLICS S-PACKAGES 3D GRAPHICS AND ANIMATION DEMO

Red Martian
14K views • 13 years ago
Real-Time In-Camera VFX for Next-Gen Filmmaking  | Project Spotlight | Unreal Engine2:15

Real-Time In-Camera VFX for Next-Gen Filmmaking | Project Spotlight | Unreal Engine

Unreal Engine
1.1M views • 7 years ago
3D Gaussian Splatting - Why Graphics Will Never Be The Same2:12

3D Gaussian Splatting - Why Graphics Will Never Be The Same

IndividualKex
2M views • 3 years ago
I painted a Landscape with Mathematics42:00

I painted a Landscape with Mathematics

Inigo Quilez
812K views • 4 years ago
Enhancing Photorealism Enhancement8:34

Enhancing Photorealism Enhancement

ISL and Collaborators
6.3M views • 5 years ago
Imaging at a trillion frames per second | Ramesh Raskar11:02

Imaging at a trillion frames per second | Ramesh Raskar

TED
3.2M views • 14 years ago
Brigade 3.0 preview - Real-time path tracing2:13

Brigade 3.0 preview - Real-time path tracing

icelaglace
439K views • 12 years ago
elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)3:36

elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)

Demoscene High-Quality Videos (Annikras)
317K views • 15 years ago
NVScene 2015 Session: How to Create Content with Signed Distance Functions (Johann Korndörfer)51:06

NVScene 2015 Session: How to Create Content with Signed Distance Functions (Johann Korndörfer)

NVScene
35K views • 11 years ago