Carl Marshall

Carl Marshall

Auto-generated profile, based on publicly available information

Carl Marshall

Meta

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2025 in Computer Graphics Forum
Verified
Journal Article
Closed access
NMN. Milef
N. Milef
DSD. Seyb
D. Seyb
TKT. Keeler
T. Keeler
TNT. Nguyen‐Phuoc
T. Nguyen‐Phuoc
ABA. Božič
A. Božič
CMC. Marshall
C. Marshall

10 December 2023
Verified
Conference Paper
Open access
SDSayantan Datta
Sayantan Datta
CMCarl Marshall
Carl Marshall
ZDZhao Dong
Zhao Dong
ZLZhengqin Li
Zhengqin Li
DNDerek Nowrouzezahrai
Derek Nowrouzezahrai
We introduce differentiable indirection – a novel learned primitive that employs differentiable multi-scale lookup tables as an effective substitute for traditional compute and data operations across the graphics pipeline. We demonstrate its flexibility on a number of graphics tasks, i.e., geometric and image representation, texture mapping, shading, and radiance field representation. In all cases, differentiable indirection seamlessly integrates into existing architectures, trains rapidly, and yields both versatile and efficient results.


4 December 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
ECEthan Chen
Ethan Chen
SKSushant Kondguli
Sushant Kondguli
CMCarl Marshall
Carl Marshall
YZYuhao Zhu
Yuhao Zhu
We introduce a gaze-tracking-free method to reduce OLED display power consumption in VR with minimal perceptual impact. This technique exploits the time course of chromatic adaptation, the human visual system's ability to maintain stable color perception under changing illumination. To that end, we propose a novel psychophysical paradigm that models how human adaptation state changes with the scene illuminant. We exploit this model to compute an optimal illuminant shift trajectory, controlling the rate and extent of illumination change, to reduce display power under a given perceptual loss budget. Our technique significantly improves the perceptual quality over prior work that applies illumination shifts instantaneously. Our technique can also be combined with prior work on luminance dimming to reduce display power by 31% with no statistical loss of perceptual quality.

1 January 2026 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
WLWeikai Lin
Weikai Lin
SZSheng Zhao
Sheng Zhao
IRIan Ross
Ian Ross
CMCarl Marshall
Carl Marshall
SKSushant Kondguli
Sushant Kondguli
YZYuhao Zhu
Yuhao Zhu