AI Restores Lost Detail in William Merritt Chase's A Comfortable Corner
AI imaging helped Parrish Art Museum conservators recover lost detail in Chase's A Comfortable Corner, altered by a 1960s restoration. The work returns to view on 14 November.

Programme
- AI helped restore Chase's A Comfortable Corner (c. 1888), altered by at least two earlier restorations including a major 1960s intervention.
- The restored painting goes on view at the Parrish Art Museum on 14 November, in a show running until 21 March 2027.
- Conservator Suzanne Siano's team used AI to combine a pre-1960s photograph with a colour image of the painting.
- The project was supported by a Bank of America grant and was the studio's first use of AI in painting conservation.
By Elena Vasquez
Artificial intelligence has helped conservators recover lost detail in William Merritt Chase's painting A Comfortable Corner (around 1888), which had been substantially altered by at least two earlier restorations, including a major intervention in the 1960s. The newly restored work belongs to the Parrish Art Museum in Water Mill, New York, and goes on view on 14 November in the exhibition William Merritt Chase and Walter Granville-Smith: American Impressionists of the East End, running until 21 March 2027.
What did the earlier restorations do?
The 1960s treatment and at least one other restoration changed the painting's appearance in several ways:
- A heavyweight, almost burlap-like lining was added.
- Retouching and blotchy inpainting covered original passages.
- Uneven varnishes discoloured over time and altered the surface texture of various areas.
- The work was apparently reduced in size, perhaps to fit a new stretcher or because damaged edges were folded over and effectively removed.
The museum worked with conservator Suzanne Siano and her team at Modern Art Conservation to prepare the painting for the exhibition.
What did the AI actually uncover?
A crucial piece of evidence was an early black-and-white photograph, understood to predate the 1960s restoration. It showed that more of the composition had once been visible. A curl of hair beneath the sitter's ear had disappeared, parts of a decorative screen had become faint or vanished, and delicate passages had been overpainted with heavier marks.
The team combined the historical photograph with a colour image of the painting using AI to create a composite showing where the two diverged. "Although we are reasonably adept with Photoshop, we felt it was worth seeing what AI could offer," Siano told The Art Newspaper. "It proved very helpful, largely because of its speed. It was not instantaneous, but it was considerably faster than assembling the comparison manually."
The composite guided closer examination. One discovery concerned Chase's signature, which had become extremely faint, with some letters apparently covered by overpaint. Because the signature is relatively abstract, Siano believes it may have been mistaken for part of the carpet pattern during the earlier restoration.
The conservators also found evidence of pentimenti — changes made by Chase himself — that were not visible in the earlier photograph, adding complexity to the analysis.
Could earlier conservators have erased Chase's own changes?
Siano raises the possibility. "It is difficult to establish whether all of these changes resulted from earlier conservation," she said. "Some of it may have stemmed from a misreading of what the conservator was seeing. They may have been cleaning toward what they believed to be the original surface when, in fact, some of what they removed may have been changes or additions made by the artist."
The team did not reinstate every discrepancy the software identified. The historical photograph was neither high-resolution nor necessarily a record of the painting's earliest state. Its evidence was weighed against magnified examination, ultraviolet imaging, knowledge of Chase's materials and comparison with his other works.
Tool, not solution
The project, supported by a Bank of America grant, was the first time Siano's studio used AI in painting conservation. "Tasks that once took considerable time can be completed more quickly, and AI can provide additional information for us to weigh," Siano said. "Ultimately, however, conservation is carried out by a highly skilled individual or team, and we do not expect that to change."
She expects AI's use in determining treatment to remain case-specific, but sees it growing as a research tool, for example in locating historical images or relevant source material. "Conservation is a combination of science, art history, craft, manual skill and artistry," Siano said. "AI is none of those things."
Why the painting matters
A Comfortable Corner depicts a woman reclining in an elaborately furnished interior, dressed in a deep blue kimono and holding an uchiwa fan. "A Comfortable Corner is an important work within William Merritt Chase's oeuvre as it depicts a specific moment in 19th-century art and Chase's own period with influences of art and design from Japan," said Kaitlin Halloran, the museum's associate curator.
Chase was a prominent figure in Gilded Age New York who spent time on Long Island's East End, where the Parrish is located. The museum holds a substantial body of his work alongside archival material donated by the artist's family.
"The judgments conservators make are nuanced and subtle, and we doubt those qualities can be replicated by a machine," Siano said. Visitors can weigh the results themselves when the restored canvas goes on display in November.
Source: theartnewspaper.com
More from Elena Vasquez
Show full bio
Senior reporter covering technology and product news in arts in the broadest sense at Arts & Voices.
1,334 articles



